/kinetic-multicam: One Take → Kinetic Supers + Camera Snaps Agent Skill

Use when the user drops or points at a local talking-head video and wants the kinetic supers + rapid camera reposition prompt for…

Context cost
7.7k tokensestimated from the bundle, loaded when it triggers
Bundle
7 files · 49.6 kB3 scripts among them — read before you run
Licence
MITthe author’s own terms
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Use when the user drops or points at a local talking-head video and wants the kinetic supers + rapid camera reposition prompt for video-to-video AI (one real take turned into split-second camera snaps that lock off, with bold motion-graphics text synced to the speech). Triggers on /kinetic-multicam, "kinetic supers", "kinetic typography video", a dropped .mp4 plus a motion-graphics-text + camera request. PT examples for reliability, "faz o prompt de kinetic supers desse vídeo", "gera supers cinéticos com cortes de câmera", "bota motion graphics e câmera nesse take".

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

contentprompt

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md24.0 kB · preview
--- name: kinetic-multicam ---
6# /kinetic-multicam: One Take → Kinetic Supers + Camera Snaps
7
8## Overview
9
10Turns ONE real talking-head take into the proven video-to-video prompt — best on **Seedance 2.0 Fast** (Google Omni runs it but with clearly weaker results; don't recommend it) — that adds two things to the untouched footage: split-second visible camera whips — motion-blurred moves that lock into stable frames on arrival — and bold kinetic supers (motion-graphics text, NOT captions) synced to the speech beats. The prompt **preserves the uploaded source video** — face, room, audio, lip sync all frozen. It does NOT describe or regenerate the scene.
11
12Core principle: **the template is frozen; only three zones ever change** — the [Xs] timestamps (always), the "[TEXT]" supers (cut from the words actually spoken; not every block gets one — supers follow their own density rule), and the camera position descriptions (only if the user asks).
13
14Sibling skill, not the same skill: /multicam does hard cuts with no text. NEVER mix the two templates — this one never says "hard cut", uses From [Xs] to [Xs] ranges (not * At [Xs]:), and carries its own typography direction. The transition itself is the differential: /multicam CUTS between angles; this skill TRAVELS between them with a visible motion-blurred whip.
15
16## Input
17
18Local video file only (the user's own footage). If the user only has a URL (an Instagram link, a Drive link), ask them to save the video as a local file first. If more than one video could be "the video", ask — never guess via ls -t.
19
20## Step 0 — Preflight (first run, or on any missing-tool error)
21
22```bash
23python "<this skill's base directory>/scripts/check_env.py"
24```
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md3,950 words
Files7
LicenceMIT
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈150
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
7,575
on trigger
The instruction body and 6 supporting files, read only when the skill fires.
3.9%
of a 200k window
Ten skills this size would take about 39% of the window before you open a file.
050k100k150k200k context window

7.7k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

7 files, 49.6 kB on disk. Mostly text — the instructions the model reads — with 3 scripts in it that your client would run only if the instructions tell it to. 1 file of its source is not in the download — listed after these, with why.

  • SKILL.md24.0 kB
  • LICENSE1.1 kB
  • README.md5.7 kB
  • requirements.txt0.1 kB
  • scripts/beats.py8.1 kB
  • scripts/check_env.py3.3 kB
  • scripts/verify_prompt.py7.3 kB

Not in the download

Not carried is a type a skill download does not hold. Take it from its source.

  • .gitignorenot carried
What is not in it

A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 3 scripts beside the text, so the download is 7 files — not the whole of its source: 1 file is left out. It is listed under the files, with why. The MIT licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# /kinetic-multicam: One Take → Kinetic Supers + Camera Snaps · 7.7k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/kinetic-multicam-one-take-kinetic-supers-camera-s/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/kinetic-multicam-one-take-kinetic-supers-camera-s" ] && { [ ! -e .claude/skills/kinetic-multicam-one-take-kinetic-supers-camera-s ] || { mv .claude/skills/kinetic-multicam-one-take-kinetic-supers-camera-s "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/kinetic-multicam-one-take-kinetic-supers-camera-s" .claude/skills/ && echo "Installed .claude/skills/kinetic-multicam-one-take-kinetic-supers-camera-s"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add aipauloshimas/kinetic-multicam-one-take-kinetic-supers-camera-s

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/kinetic-multicam-one-take-kinetic-supers-camera-s/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/kinetic-multicam-one-take-kinetic-supers-camera-s/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/kinetic-multicam-one-take-kinetic-supers-camera-s" ] && { [ ! -e ~/.claude/skills/kinetic-multicam-one-take-kinetic-supers-camera-s ] || { mv ~/.claude/skills/kinetic-multicam-one-take-kinetic-supers-camera-s "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/kinetic-multicam-one-take-kinetic-supers-camera-s" ~/.claude/skills/ && echo "Installed ~/.claude/skills/kinetic-multicam-one-take-kinetic-supers-camera-s" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/kinetic-multicam-one-take-kinetic-supers-camera-s/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. It appears as kinetic-multicam in Gemini CLI, Codex, Copilot and Grok (its own name); Claude Code lists it by the folder name, kinetic-multicam-one-take-kinetic-supers-camera-s. Not in this download: 1 file of its source (which one, and why). Take it from its source.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referenceaipauloshimas/kinetic-multicam-one-take-kinetic-supers-camera-s

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

AI
aipauloshimas

Publishes on mcprush.

0 servers listed1 skill listednot claimed
Profile
Publisher
Servers0
Claim this skill